A Review on Objective-Driven Artificial Intelligence

TL;DR

This paper reviews the current state of artificial intelligence, highlighting its limitations in understanding context and common sense, and explores hierarchical planning and energy-based methods as promising avenues to bridge the gap with human intelligence.

Contribution

It provides a comprehensive review of AI limitations and discusses advanced approaches like hierarchical planning and energy-based models to enhance AI's cognitive capabilities.

Findings

Current AI techniques lack human-like understanding of context.

Hierarchical planning approaches show promise in closing the intelligence gap.

Energy-based and latent-variable methods are promising research directions.

Abstract

While advancing rapidly, Artificial Intelligence still falls short of human intelligence in several key aspects due to inherent limitations in current AI technologies and our understanding of cognition. Humans have an innate ability to understand context, nuances, and subtle cues in communication, which allows us to comprehend jokes, sarcasm, and metaphors. Machines struggle to interpret such contextual information accurately. Humans possess a vast repository of common-sense knowledge that helps us make logical inferences and predictions about the world. Machines lack this innate understanding and often struggle with making sense of situations that humans find trivial. In this article, we review the prospective Machine Intelligence candidates, a review from Prof. Yann LeCun, and other work that can help close this gap between human and machine intelligence. Specifically, we talk about what's lacking with the current AI techniques such as supervised learning, reinforcement learning, self-supervised learning, etc. Then we show how Hierarchical planning-based approaches can help us close that gap and deep-dive into energy-based, latent-variable methods and Joint embedding predictive architecture methods.